Menu
mutinaiPreview: Public preview · figures are illustrative fixture data, attributed to their source · data to May 2025 · read-only
What can I run?
What can I run? · 8K context

RTX 4060 Ti 16GB budget build (32 GB DDR5)

Change hardwareCurrently: RTX 4060 Ti 16GB budget build (32 GB DDR5)
Not sure what you have? Help me checkTwo numbers decide it: memory, and whether there is a graphics card

On a Mac

Click the Apple logo in the top-left corner of the screen, then About This Mac. Note the Chip (M1, M2, M3, M4…) and the Memory (8 GB, 16 GB…).

On Windows

Press Ctrl + Shift + Esc to open Task Manager, then Performance. Memory shows your RAM. If a GPU entry lists Dedicated GPU memory of 4 GB or more, you have a graphics card; otherwise you don’t.

Then pick the closest match — or the Build your own setup option below for anything else:

Mac with 8 GBMac with 16 GBWindows laptop, 16 GB, no graphics cardPC with a 16 GB graphics card

Still unsure? Start with the 16 GB laptop: what runs there runs on almost any recent computer.

Laptops

MacBook Air M1 8 GBMacBook Air M2 16 GBMacBook Air M3 16 GBMacBook Air M4 16 GBMacBook Pro M3 Max 64 GBMacBook Pro M4 Max 128 GBWindows laptop 16 GB

Mini PCs

GB10 mini workstationMac mini M4 16 GBMac mini M4 Pro 48 GBRyzen AI Max+ 395 mini PC

Desktops

CPU-only Ryzen 9 7950XDual RTX 3090Mac Studio M2 Ultra 192 GBRTX 4060 Ti 16GB budget buildRTX 4090 workstationRTX 5090 workstationRX 7900 XTX desktop

Servers

A100 80GB server
Build your own setupChoose GPUs or a chip and how much memory you have
8run well
9with offload
2too large

Speeds marked measured come from reference results and verified community runs on this exact system; others are estimates.

Start with this one

Phi-4

General-purpose model for reasoning and coding. From Microsoft.

Speed
Types faster than you can read estimate~20 tok/s estimate
Download
8.3 GiBQ4_K_M
Memory
10.7 of 15.2 GB estimatefits entirely
License
PermissiveMIT License

Why this one: a general chat model that fits this machine without spilling out of memory, answers faster than you read, and has the strongest benchmark results among those that do.

Now run it

Easiest: LM Studio free desktop app, no terminal

  1. Download LM Studio from lmstudio.ai, install it and open it.
  2. Open the search tab (the magnifying glass) and search for lmstudio-community/phi-4-GGUF.
  3. Choose the Q4_K_M download (8.3 GiB) and click Download.
  4. Go to the chat tab, pick Phi-4 at the top, and type your first message.

In a terminal: Ollama one command

  1. Install Ollama from ollama.com/download.
  2. Open a terminal and run:
    ollama run hf.co/lmstudio-community/phi-4-GGUF:Q4_K_M
    The first run downloads the model (8.3 GiB); then type a message and press Enter.

Everything that runs here grouped by how it runs

Runs in accelerator memory 8

Fits entirely in GPU or unified memory — the fast path.

ModelRecommended downloadMemoryGeneration speed
Variant Qwen2.5 14B InstructQwen Team (Alibaba Cloud) · 14.8B
2 other options
AWQ 4-bit · Qwen Team (Alibaba Cloud)SGLangRuns well10.2 GiB~21 tok/s estimate
Q6_K · LM Studio Communityllama.cppTight fit13.7 GiB~15 tok/s estimate
Q4_K_M via llama.cpp8.4 GiB · Qwen Team (Alibaba Cloud)
10.7 of 15.2 GiB estimate
25.5 tok/s measured
Variant Phi-4Microsoft · 14.7B
1 other option
Q8_0 · LM Studio Communityllama.cppWith offload17.1 GiB~9 tok/s estimate
Q4_K_M via llama.cpp8.3 GiB · LM Studio Community
10.7 of 15.2 GiB estimate
~20 tok/s estimate
Variant Gemma 2 9B ITGoogle DeepMind · 9.24BQ4_K_M via llama.cpp5.3 GiB · LM Studio Community
8.6 of 15.2 GiB estimate
~30 tok/s estimate
Variant Hermes 3 Llama 3.1 8BMeta · 8.03B
2 other options
Q4_K_M · NousResearchllama.cppRuns well6.3 GiB~34 tok/s estimate
Q6_K · NousResearchllama.cppRuns well7.9 GiB~26 tok/s estimate
Q8_0 via llama.cpp8.0 GiB · NousResearch
9.8 of 15.2 GiB estimate
~21 tok/s estimate
Variant Llama 3.1 8B InstructMeta · 8.03B
2 other options
Q4_K_M · LM Studio Communityllama.cppRuns well6.3 GiB~34 tok/s estimate
FP8 · RedHatAISGLangRuns well10.3 GiB~20 tok/s estimate
Q8_0 via llama.cpp7.9 GiB · LM Studio Community
9.8 of 15.2 GiB estimate
~21 tok/s estimate
Variant Qwen2.5 7B InstructQwen Team (Alibaba Cloud) · 7.62B
2 other options
AWQ 4-bit · Qwen Team (Alibaba Cloud)SGLangRuns well5.2 GiB~38 tok/s estimate
Q4_K_M · Qwen Team (Alibaba Cloud)llama.cppRuns well5.5 GiB~36 tok/s estimate
Q8_0 via llama.cpp7.5 GiB · Qwen Team (Alibaba Cloud)
8.8 of 15.2 GiB estimate
~22 tok/s estimate
Variant DeepSeek-R1-Distill-Qwen-7BQwen Team (Alibaba Cloud) · 7.62BQ4_K_M via llama.cpp4.3 GiB · LM Studio Community
5.2 of 15.2 GiB estimate
~36 tok/s estimate
Variant Mistral 7B Instruct v0.3Mistral AI · 7.25B
1 other option
Q4_K_M · LM Studio Communityllama.cppRuns well5.8 GiB~38 tok/s estimate
Q8_0 via llama.cpp7.2 GiB · LM Studio Community
9.0 of 15.2 GiB estimate
~23 tok/s estimate

Runs with partial offload to system RAM 9

Too big for accelerator memory alone; part of it runs from system RAM, which is much slower.

ModelRecommended downloadMemoryGeneration speed
Variant Llama 3.3 70B InstructMeta · 70.6BQ3_K_M via llama.cpp32.1 GiB · Unsloth AI
36.4 of 15.2 GiB · 21.2 in RAM estimate
~2 tok/s estimate
Variant Mixtral 8x7B Instruct v0.1Mistral AI · 46.7B (12.9B active)Q4_K_M via llama.cpp26.6 GiB · LM Studio Community
29.1 of 15.2 GiB · 13.9 in RAM estimate
~11 tok/s estimate
Variant Qwen2.5 32B InstructQwen Team (Alibaba Cloud) · 32.8B
1 other option
Q5_K_M · LM Studio Communityllama.cppWith offload25.1 GiB~4 tok/s estimate
Q4_K_M via llama.cpp18.7 GiB · Qwen Team (Alibaba Cloud)
21.9 of 15.2 GiB · 6.7 in RAM estimate
~5 tok/s estimate
Variant Qwen2.5-Coder 32B InstructQwen Team (Alibaba Cloud) · 32.8B
1 other option
Q8_0 · LM Studio Communityllama.cppWith offload36.2 GiB~2 tok/s estimate
Q4_K_M via llama.cpp18.7 GiB · Qwen Team (Alibaba Cloud)
21.9 of 15.2 GiB · 6.7 in RAM estimate
~5 tok/s estimate
Variant DeepSeek-R1-Distill-Qwen-32BQwen Team (Alibaba Cloud) · 32.8BQ4_K_M via llama.cpp18.7 GiB · LM Studio Community
21.9 of 15.2 GiB · 6.7 in RAM estimate
~5 tok/s estimate
Variant Qwen3 30B-A3BQwen Team (Alibaba Cloud) · 30.5B (3.3B active)
3 other options
Q4_K_M · Unsloth AIllama.cppWith offload19.3 GiB~50 tok/s estimate
Q8_0 · LM Studio Communityllama.cppWith offload32.7 GiB~22 tok/s estimate
Q8_0 · Qwen Team (Alibaba Cloud)llama.cppWith offload32.7 GiB~21 tok/s estimate
Q4_K_M via llama.cpp17.3 GiB · Qwen Team (Alibaba Cloud)
19.2 of 15.2 GiB · 4.0 in RAM estimate
~50 tok/s estimate
Variant Gemma 3 27B ITGoogle DeepMind · 27.4BQ4_K_M via llama.cpp15.6 GiB · LM Studio Community
20.6 of 15.2 GiB · 5.4 in RAM estimate
~6 tok/s estimate
Variant Gemma 2 27B ITGoogle DeepMind · 27.2BQ4_K_M via llama.cpp15.5 GiB · LM Studio Community
19.5 of 15.2 GiB · 4.3 in RAM estimate
~7 tok/s estimate
Variant Mistral Small 24B Instruct 2501Mistral AI · 23.6B
1 other option
Q6_K · LM Studio Communityllama.cppWith offload20.5 GiB~6 tok/s estimate
Q4_K_M via llama.cpp13.4 GiB · LM Studio Community
15.7 of 15.2 GiB · 0.5 in RAM estimate
~12 tok/s estimate
Too large for this hardware2 model variants
How this is calculatedMemory, fit and speed estimates

Memory = download size + fp16 KV cache for 8K tokens + runtime overhead. Usable memory is 95% of dedicated VRAM, a device-specific share of unified memory (75% by default), and 80% of system RAM for runtimes that can offload. Runtimes must load the file format and support a backend present on the hardware.

Estimated speed is bounded by memory bandwidth ÷ bytes read per token (active parameters for mixture-of-experts), shown in italics with an estimate label and a ±35% range (hover for it). Measured speeds are medians of reference results and verified public community runs on the same system, download and runtime. For each model we recommend the highest-precision download that fits, preferring not to offload.